Find .md files that contain non-ascii characters except long dash '—' and three dots '…'. If file 'some.md' needs sanitizing, save sanizitized version as 'some.ii'.

SANITIZE_md.py

#!/usr/bin/python3

'''
Find all .md files that contain non-ascii characters excluding '—…'

If such file found, sanitize it and save as NAME.ii
'''

import glob, re

g_allowed = re.compile(r'[^\x00-\x7F—…]')

def do_with_file(i):
    with open(i, 'rb') as ii:
        if test_file(ii):
            return
    print("Caught file " + i)
    o = i[:-3] + '.ii'
    with open(i, 'rb') as ii:
        with open(o, 'wb') as oo:
            conv(ii, oo)

def test_file(i):
    for j in i:
        k = j.decode('utf-8')
        if re.findall(g_allowed, k):
            return False
    return True

def conv(i, o):
    for j in i:
        k = j.decode('utf-8')
        c = re.sub(g_allowed, '', k)
        o.write(c.encode('utf-8'))

for f in glob.glob('./**/*.md', recursive=True):
    do_with_file(f)